SBIR/STTR Research Award
AutoCategorization for Customized Knowledge Portals
Award amount
$69,487Program and phase
SBIR · Phase IAward year
2004Award details
- Awarding agency
- National Aeronautics and Space Administration
- Branch
- Not reported
- Recipient company
- Taxonomize
- Proposal award date
- 2004-01-16
- Contract end date
- 2004-07-19
- UEI
- Not reported
- Solicitation number
- Not reported
- Topic code
- A5.01
Research abstract
An AutoCategorizing Knowledge Management Engine ("AKM") will automate key capabilities for both human-human and human-agent collaboration tools in aerospace information systems:
* Automatic organization of shared and new information, by a standards-based interface to other knowledge tools, based on an effective auto-categorization engine;
* Immediate incorporation of new knowledge into auto-updated taxonomies, and extension for new topics;
* Automatically updated knowledge organizations for groups, individuals, and specialized activities;
* Knowledge discovery of new and emerging themes in data and discussions.
The result is that AKM will:
* Improve usability and collaboration potential for shared sites of working, learning, and discussion;
* Help to build communities of practice for growing technical efforts such as the NASA Taxonomy;
* Speed and improve sharing of knowledge within NASA and with its larger community;
* Help to evolve the shared, developing, interoperating NASA ontologies.
AKM will be prototyped in Phase I as an extension of three existing products (Taxonomize's Auto-Categorizer, Resource Aid, and Stochastic Analyzer) and applied to selected NASA information programs. In Phase II AKM will be productized for extended NASA, government, and commercial application.
Technology keywords
Not reported
Awards with the same topic code
Verified by an exact topic code match. This is not a text-similarity match.
- UAS Demand Generation and Airspace Performance Impact Prediction
- Rapid Automated Mission Planning System
- UAS Demand Generation and Airspace Performance Impact Prediction
- Real-time Estimation of UAS Performance Using Efficient Sampling of Functional Models
- Rapid Automated Mission Planning System